54 CHAPTER 3. VECTOR SPACES

Example 3.1.4 Determine whether the real valued functions defined on R given by thepolynomials

x2 +2x+1,x2 +2x,x2 + x+1

are independent with field of scalars R.

Suppose a(x2 +2x+1

)+b(x2 +2x

)+ c(x2 + x+1

)= 0 then differentiate both sides

to obtain a(2x+2)+b(2x+2)+c(2x+1) = 0. Now differentiate again. This yields 2a+2b+2c = 0. In the second equation, let x =−1. Then −c = 0 so c = 0. Thus

a(x2 +2x+1

)+b(x2 +2x

)= 0

a+b = 0

Now let x = 0 in the top equation to find that a = 0. Then from the bottom equation, itfollows that b = 0 also. Thus the three functions are linearly independent.

The main theorem is the following, called the replacement or exchange theorem. It usesthe argument of the second half of the above proposition repeatedly.

Theorem 3.1.5 Let {u1, · · · ,ur} ,{v1, · · · ,vs} be subsets of a vector space V with field ofscalars F and suppose {u1, · · · ,ur} is linearly independent and each ui ∈ span(v1, · · · ,vs) .Then r ≤ s. In words, linearly independent sets are no longer than spanning sets.

Proof: Say r > s. By assumption, u1 = ∑i bivi. Not all of the bi can equal 0 because ifthis were so, you would have u1 = 0 which would violate the assumption that {u1, · · · ,ur}is linearly independent. You could write

1u1 +0u2 + · · ·+0ur = 0

since u1 = 0. Thus some vi say vi1 is a linear combination of the vector u1 along with the v jfor j ̸= i. It follows that the span of {u1,v1, · · · , v̂i1 , · · · ,vn} includes each of the ui wherethe hat indicates that vi1 has been omitted from the list of vectors. Now suppose each ui isin

span(u1 · · · ,uk,v1, · · · , v̂i1 , · · · , v̂ik · · · ,vs

)where the vectors v̂i1 , · · · , v̂ik have been omitted for k ≤ s. Then there are scalars ci and disuch that

uk+1 =k

∑i=1

ciui + ∑j/∈{i1,··· ,ik}

d jv j

By the assumption that {u1, · · · ,ur} is linearly independent, not all of the d j can equal 0.Why? Therefore, there exists ik+1 /∈ {i1, · · · , ik} such that dik ̸= 0. Hence one can solve forvik+1 as a linear combination of {u1, · · · ,ur} and the v j for j /∈ {i1, · · · , ik, ik+1}. Thus wecan replace this vik+1 by a linear combination of these vectors, and so the u j are in

span(u1, · · · ,uk,uk+1,v1, · · · , v̂i1 , · · · , v̂ik , v̂ik+1 , · · · ,vs

)Continuing this replacement process, it follows that since r > s, one can eliminate all of thevectors {v1, · · · ,vs} and obtain that the ui are contained in span(u1, · · · ,us) . But then youwould have us+1 ∈ span(u1, · · · ,us) which is impossible since these vectors {u1, · · · ,ur}are linearly independent. It follows that r ≤ s. ■

Next is the definition of dimension and basis of a vector space.

54 CHAPTER 3. VECTOR SPACESExample 3.1.4 Determine whether the real valued functions defined on R given by thepolynomialsx? + 2x4 Lx? +2x,27 +x41are independent with field of scalars R.Suppose a (x? + 2x +1) +b (x? + 2x) +c (x? +x+ 1) =0 then differentiate both sidesto obtain a(2x+2)+b(2x+2)+c(2x+1) =0. Now differentiate again. This yields 2a+2b+2c = 0. In the second equation, let x = —1. Then —c = 0 soc = 0. Thusa(x?+2x+1) +b (x? +2x) = 0a+b = 0Now let x = 0 in the top equation to find that a = 0. Then from the bottom equation, itfollows that b = 0 also. Thus the three functions are linearly independent.The main theorem is the following, called the replacement or exchange theorem. It usesthe argument of the second half of the above proposition repeatedly.Theorem 3.1.5 Let {u,,--- ,u-},{vi,--+ ,vs} be subsets of a vector space V with field ofscalars F and suppose {u,--- ,u,} is linearly independent and each u; € span(v1,--- ,Vs)-Then r < s. In words, linearly independent sets are no longer than spanning sets.Proof: Say r > s. By assumption, uw; = Y;5;v;. Not all of the b; can equal 0 because ifthis were so, you would have u; = 0 which would violate the assumption that {uw ),--- ,u,}is linearly independent. You could writelu; +0u2 +---+0u, =0since u; = 0. Thus some v; say v;, is a linear combination of the vector u; along with the v;for j #i. It follows that the span of {u1,v1,--- ,%j,,--+ ,Vn} includes each of the u; wherethe hat indicates that v;, has been omitted from the list of vectors. Now suppose each uy; isinspan (uw) +: Ue Vis Vist Pig tt Vs)where the vectors ¥;,,--- ,¥;, have been omitted for k < s. Then there are scalars c; and d;such thatkUK+1 =) cut y’ djvji=l JELi 1 ste}By the assumption that {w,--- ,u,} is linearly independent, not all of the dj can equal 0.Why? Therefore, there exists iz, ¢ {i1,--- ,i¢} such that d;, 4 0. Hence one can solve forVj,,, a8 a linear combination of {u1,---,u,} and the v; for j ¢ {i1,--- ,ix,ic41}. Thus wecan replace this v;,,, by a linear combination of these vectors, and so the uj; are inspan (uy,+-* Ug, UR+1,V15°°* Vist: Vig Vigne? Vs)Continuing this replacement process, it follows that since r > s, one can eliminate all of thevectors {v;,---,vs} and obtain that the u; are contained in span (uj,--- ,us). But then youwould have us41 € span(u1,--- ,Us) which is impossible since these vectors {u1,--- ,u,}are linearly independent. It follows that r <5.Next is the definition of dimension and basis of a vector space.